Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    components and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mijn
    0.57
     hade
    0.48
     är
    0.46
     ከ
    0.45
     hebben
    0.45
     ebenfalls
    0.45
     was
    0.44
     havde
    0.44
    も
    0.43
     میرے
    0.43
    POSITIVE LOGITS
    শালী
    0.46
    OrCreate
    0.41
    ஜ
    0.41
     लक्षणों
    0.40
    each
    0.40
    Creating
    0.39
     каждая
    0.39
    रल
    0.39
     sẵn
    0.39
    getWriter
    0.39
    Act Density 0.052%

    No Known Activations